The buildup of huge data within business intelligence is essential because such data includes complete conceptual and technological stack in addition to raw and processed data, data management, and analytics. Evaluating Data Quality Model Based-In-Use has gained more ground since business value could be only estimated in its used context. Despite the numerous data quality models used for regular data quality assessment, none of them have been amended to big data. For this reason, we propose four efficiencies and four metabolism processes as data quality indicators usable in big data researches. This model appropriately obtained the quality in use levels of the entry data for big data analytics, and those adequacies of Data Quality Model Based-In-Use levels could be comprehended as dependability indicators and adequacy of big data investigation. Besides, we have demonstrated the practical examples along with a proposed method, the stacked recurrent neural network for data quality assessment. Therefore, this model being independent of any pre-conditions or technologies could be integrated into various big data research.

中文翻译：

---

采用人类代谢过程作为基于数据质量的模型

在商业智能中积累大量数据至关重要，因为此类数据除了原始数据和处理数据、数据管理和分析之外，还包括完整的概念和技术堆栈。评估基于使用的数据质量模型已经取得了更多的进展，因为只能在其使用的上下文中估计业务价值。尽管用于常规数据质量评估的数据质量模型众多，但没有一个被修改为大数据。为此，我们提出四种效率和四种代谢过程作为可用于大数据研究的数据质量指标。该模型恰当地获取了大数据分析入口数据的使用质量等级，将基于数据质量模型使用等级的充分性理解为大数据调查的可靠性指标和充分性。此外，我们还展示了实际示例以及所提出的方法，即用于数据质量评估的堆叠递归神经网络。因此，这种独立于任何前提条件或技术的模型可以集成到各种大数据研究中。